Upload translation_mt5_k.ipynb
Browse files- translation_mt5_k.ipynb +1778 -0
translation_mt5_k.ipynb
ADDED
|
@@ -0,0 +1,1778 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"nbformat": 4,
|
| 3 |
+
"nbformat_minor": 0,
|
| 4 |
+
"metadata": {
|
| 5 |
+
"colab": {
|
| 6 |
+
"provenance": [],
|
| 7 |
+
"gpuType": "T4"
|
| 8 |
+
},
|
| 9 |
+
"kernelspec": {
|
| 10 |
+
"name": "python3",
|
| 11 |
+
"display_name": "Python 3"
|
| 12 |
+
},
|
| 13 |
+
"language_info": {
|
| 14 |
+
"name": "python"
|
| 15 |
+
},
|
| 16 |
+
"accelerator": "GPU",
|
| 17 |
+
"widgets": {
|
| 18 |
+
"application/vnd.jupyter.widget-state+json": {
|
| 19 |
+
"8a49fb7918744d23bf64237c2674fc6b": {
|
| 20 |
+
"model_module": "@jupyter-widgets/controls",
|
| 21 |
+
"model_name": "HBoxModel",
|
| 22 |
+
"model_module_version": "1.5.0",
|
| 23 |
+
"state": {
|
| 24 |
+
"_dom_classes": [],
|
| 25 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 26 |
+
"_model_module_version": "1.5.0",
|
| 27 |
+
"_model_name": "HBoxModel",
|
| 28 |
+
"_view_count": null,
|
| 29 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 30 |
+
"_view_module_version": "1.5.0",
|
| 31 |
+
"_view_name": "HBoxView",
|
| 32 |
+
"box_style": "",
|
| 33 |
+
"children": [
|
| 34 |
+
"IPY_MODEL_7a64e72d88084b6897d53c344aad4358",
|
| 35 |
+
"IPY_MODEL_85b34cfea65c4a8dbdae30a8eec22a98",
|
| 36 |
+
"IPY_MODEL_500b7fb2607c4eebbb5bea0bfc4e33ff"
|
| 37 |
+
],
|
| 38 |
+
"layout": "IPY_MODEL_b53f4a68898e45098d6801e4987e4c10"
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"7a64e72d88084b6897d53c344aad4358": {
|
| 42 |
+
"model_module": "@jupyter-widgets/controls",
|
| 43 |
+
"model_name": "HTMLModel",
|
| 44 |
+
"model_module_version": "1.5.0",
|
| 45 |
+
"state": {
|
| 46 |
+
"_dom_classes": [],
|
| 47 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 48 |
+
"_model_module_version": "1.5.0",
|
| 49 |
+
"_model_name": "HTMLModel",
|
| 50 |
+
"_view_count": null,
|
| 51 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 52 |
+
"_view_module_version": "1.5.0",
|
| 53 |
+
"_view_name": "HTMLView",
|
| 54 |
+
"description": "",
|
| 55 |
+
"description_tooltip": null,
|
| 56 |
+
"layout": "IPY_MODEL_008567f59c13464b82ca3946ccf0058c",
|
| 57 |
+
"placeholder": "",
|
| 58 |
+
"style": "IPY_MODEL_6ac91c5649bc4b6fa0d3860e71cdb01b",
|
| 59 |
+
"value": "Map: 100%"
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"85b34cfea65c4a8dbdae30a8eec22a98": {
|
| 63 |
+
"model_module": "@jupyter-widgets/controls",
|
| 64 |
+
"model_name": "FloatProgressModel",
|
| 65 |
+
"model_module_version": "1.5.0",
|
| 66 |
+
"state": {
|
| 67 |
+
"_dom_classes": [],
|
| 68 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 69 |
+
"_model_module_version": "1.5.0",
|
| 70 |
+
"_model_name": "FloatProgressModel",
|
| 71 |
+
"_view_count": null,
|
| 72 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 73 |
+
"_view_module_version": "1.5.0",
|
| 74 |
+
"_view_name": "ProgressView",
|
| 75 |
+
"bar_style": "success",
|
| 76 |
+
"description": "",
|
| 77 |
+
"description_tooltip": null,
|
| 78 |
+
"layout": "IPY_MODEL_90bfdbd03ac44d5ca3df23ebcc02d863",
|
| 79 |
+
"max": 74586,
|
| 80 |
+
"min": 0,
|
| 81 |
+
"orientation": "horizontal",
|
| 82 |
+
"style": "IPY_MODEL_6618b65302df46098bd2ad029ed668eb",
|
| 83 |
+
"value": 74586
|
| 84 |
+
}
|
| 85 |
+
},
|
| 86 |
+
"500b7fb2607c4eebbb5bea0bfc4e33ff": {
|
| 87 |
+
"model_module": "@jupyter-widgets/controls",
|
| 88 |
+
"model_name": "HTMLModel",
|
| 89 |
+
"model_module_version": "1.5.0",
|
| 90 |
+
"state": {
|
| 91 |
+
"_dom_classes": [],
|
| 92 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 93 |
+
"_model_module_version": "1.5.0",
|
| 94 |
+
"_model_name": "HTMLModel",
|
| 95 |
+
"_view_count": null,
|
| 96 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 97 |
+
"_view_module_version": "1.5.0",
|
| 98 |
+
"_view_name": "HTMLView",
|
| 99 |
+
"description": "",
|
| 100 |
+
"description_tooltip": null,
|
| 101 |
+
"layout": "IPY_MODEL_a04d20d2b4934f35a7890f24546023d7",
|
| 102 |
+
"placeholder": "",
|
| 103 |
+
"style": "IPY_MODEL_5f5df2985c6f49d3816888ec4ebd9add",
|
| 104 |
+
"value": " 74586/74586 [00:44<00:00, 1302.29 examples/s]"
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
"b53f4a68898e45098d6801e4987e4c10": {
|
| 108 |
+
"model_module": "@jupyter-widgets/base",
|
| 109 |
+
"model_name": "LayoutModel",
|
| 110 |
+
"model_module_version": "1.2.0",
|
| 111 |
+
"state": {
|
| 112 |
+
"_model_module": "@jupyter-widgets/base",
|
| 113 |
+
"_model_module_version": "1.2.0",
|
| 114 |
+
"_model_name": "LayoutModel",
|
| 115 |
+
"_view_count": null,
|
| 116 |
+
"_view_module": "@jupyter-widgets/base",
|
| 117 |
+
"_view_module_version": "1.2.0",
|
| 118 |
+
"_view_name": "LayoutView",
|
| 119 |
+
"align_content": null,
|
| 120 |
+
"align_items": null,
|
| 121 |
+
"align_self": null,
|
| 122 |
+
"border": null,
|
| 123 |
+
"bottom": null,
|
| 124 |
+
"display": null,
|
| 125 |
+
"flex": null,
|
| 126 |
+
"flex_flow": null,
|
| 127 |
+
"grid_area": null,
|
| 128 |
+
"grid_auto_columns": null,
|
| 129 |
+
"grid_auto_flow": null,
|
| 130 |
+
"grid_auto_rows": null,
|
| 131 |
+
"grid_column": null,
|
| 132 |
+
"grid_gap": null,
|
| 133 |
+
"grid_row": null,
|
| 134 |
+
"grid_template_areas": null,
|
| 135 |
+
"grid_template_columns": null,
|
| 136 |
+
"grid_template_rows": null,
|
| 137 |
+
"height": null,
|
| 138 |
+
"justify_content": null,
|
| 139 |
+
"justify_items": null,
|
| 140 |
+
"left": null,
|
| 141 |
+
"margin": null,
|
| 142 |
+
"max_height": null,
|
| 143 |
+
"max_width": null,
|
| 144 |
+
"min_height": null,
|
| 145 |
+
"min_width": null,
|
| 146 |
+
"object_fit": null,
|
| 147 |
+
"object_position": null,
|
| 148 |
+
"order": null,
|
| 149 |
+
"overflow": null,
|
| 150 |
+
"overflow_x": null,
|
| 151 |
+
"overflow_y": null,
|
| 152 |
+
"padding": null,
|
| 153 |
+
"right": null,
|
| 154 |
+
"top": null,
|
| 155 |
+
"visibility": null,
|
| 156 |
+
"width": null
|
| 157 |
+
}
|
| 158 |
+
},
|
| 159 |
+
"008567f59c13464b82ca3946ccf0058c": {
|
| 160 |
+
"model_module": "@jupyter-widgets/base",
|
| 161 |
+
"model_name": "LayoutModel",
|
| 162 |
+
"model_module_version": "1.2.0",
|
| 163 |
+
"state": {
|
| 164 |
+
"_model_module": "@jupyter-widgets/base",
|
| 165 |
+
"_model_module_version": "1.2.0",
|
| 166 |
+
"_model_name": "LayoutModel",
|
| 167 |
+
"_view_count": null,
|
| 168 |
+
"_view_module": "@jupyter-widgets/base",
|
| 169 |
+
"_view_module_version": "1.2.0",
|
| 170 |
+
"_view_name": "LayoutView",
|
| 171 |
+
"align_content": null,
|
| 172 |
+
"align_items": null,
|
| 173 |
+
"align_self": null,
|
| 174 |
+
"border": null,
|
| 175 |
+
"bottom": null,
|
| 176 |
+
"display": null,
|
| 177 |
+
"flex": null,
|
| 178 |
+
"flex_flow": null,
|
| 179 |
+
"grid_area": null,
|
| 180 |
+
"grid_auto_columns": null,
|
| 181 |
+
"grid_auto_flow": null,
|
| 182 |
+
"grid_auto_rows": null,
|
| 183 |
+
"grid_column": null,
|
| 184 |
+
"grid_gap": null,
|
| 185 |
+
"grid_row": null,
|
| 186 |
+
"grid_template_areas": null,
|
| 187 |
+
"grid_template_columns": null,
|
| 188 |
+
"grid_template_rows": null,
|
| 189 |
+
"height": null,
|
| 190 |
+
"justify_content": null,
|
| 191 |
+
"justify_items": null,
|
| 192 |
+
"left": null,
|
| 193 |
+
"margin": null,
|
| 194 |
+
"max_height": null,
|
| 195 |
+
"max_width": null,
|
| 196 |
+
"min_height": null,
|
| 197 |
+
"min_width": null,
|
| 198 |
+
"object_fit": null,
|
| 199 |
+
"object_position": null,
|
| 200 |
+
"order": null,
|
| 201 |
+
"overflow": null,
|
| 202 |
+
"overflow_x": null,
|
| 203 |
+
"overflow_y": null,
|
| 204 |
+
"padding": null,
|
| 205 |
+
"right": null,
|
| 206 |
+
"top": null,
|
| 207 |
+
"visibility": null,
|
| 208 |
+
"width": null
|
| 209 |
+
}
|
| 210 |
+
},
|
| 211 |
+
"6ac91c5649bc4b6fa0d3860e71cdb01b": {
|
| 212 |
+
"model_module": "@jupyter-widgets/controls",
|
| 213 |
+
"model_name": "DescriptionStyleModel",
|
| 214 |
+
"model_module_version": "1.5.0",
|
| 215 |
+
"state": {
|
| 216 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 217 |
+
"_model_module_version": "1.5.0",
|
| 218 |
+
"_model_name": "DescriptionStyleModel",
|
| 219 |
+
"_view_count": null,
|
| 220 |
+
"_view_module": "@jupyter-widgets/base",
|
| 221 |
+
"_view_module_version": "1.2.0",
|
| 222 |
+
"_view_name": "StyleView",
|
| 223 |
+
"description_width": ""
|
| 224 |
+
}
|
| 225 |
+
},
|
| 226 |
+
"90bfdbd03ac44d5ca3df23ebcc02d863": {
|
| 227 |
+
"model_module": "@jupyter-widgets/base",
|
| 228 |
+
"model_name": "LayoutModel",
|
| 229 |
+
"model_module_version": "1.2.0",
|
| 230 |
+
"state": {
|
| 231 |
+
"_model_module": "@jupyter-widgets/base",
|
| 232 |
+
"_model_module_version": "1.2.0",
|
| 233 |
+
"_model_name": "LayoutModel",
|
| 234 |
+
"_view_count": null,
|
| 235 |
+
"_view_module": "@jupyter-widgets/base",
|
| 236 |
+
"_view_module_version": "1.2.0",
|
| 237 |
+
"_view_name": "LayoutView",
|
| 238 |
+
"align_content": null,
|
| 239 |
+
"align_items": null,
|
| 240 |
+
"align_self": null,
|
| 241 |
+
"border": null,
|
| 242 |
+
"bottom": null,
|
| 243 |
+
"display": null,
|
| 244 |
+
"flex": null,
|
| 245 |
+
"flex_flow": null,
|
| 246 |
+
"grid_area": null,
|
| 247 |
+
"grid_auto_columns": null,
|
| 248 |
+
"grid_auto_flow": null,
|
| 249 |
+
"grid_auto_rows": null,
|
| 250 |
+
"grid_column": null,
|
| 251 |
+
"grid_gap": null,
|
| 252 |
+
"grid_row": null,
|
| 253 |
+
"grid_template_areas": null,
|
| 254 |
+
"grid_template_columns": null,
|
| 255 |
+
"grid_template_rows": null,
|
| 256 |
+
"height": null,
|
| 257 |
+
"justify_content": null,
|
| 258 |
+
"justify_items": null,
|
| 259 |
+
"left": null,
|
| 260 |
+
"margin": null,
|
| 261 |
+
"max_height": null,
|
| 262 |
+
"max_width": null,
|
| 263 |
+
"min_height": null,
|
| 264 |
+
"min_width": null,
|
| 265 |
+
"object_fit": null,
|
| 266 |
+
"object_position": null,
|
| 267 |
+
"order": null,
|
| 268 |
+
"overflow": null,
|
| 269 |
+
"overflow_x": null,
|
| 270 |
+
"overflow_y": null,
|
| 271 |
+
"padding": null,
|
| 272 |
+
"right": null,
|
| 273 |
+
"top": null,
|
| 274 |
+
"visibility": null,
|
| 275 |
+
"width": null
|
| 276 |
+
}
|
| 277 |
+
},
|
| 278 |
+
"6618b65302df46098bd2ad029ed668eb": {
|
| 279 |
+
"model_module": "@jupyter-widgets/controls",
|
| 280 |
+
"model_name": "ProgressStyleModel",
|
| 281 |
+
"model_module_version": "1.5.0",
|
| 282 |
+
"state": {
|
| 283 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 284 |
+
"_model_module_version": "1.5.0",
|
| 285 |
+
"_model_name": "ProgressStyleModel",
|
| 286 |
+
"_view_count": null,
|
| 287 |
+
"_view_module": "@jupyter-widgets/base",
|
| 288 |
+
"_view_module_version": "1.2.0",
|
| 289 |
+
"_view_name": "StyleView",
|
| 290 |
+
"bar_color": null,
|
| 291 |
+
"description_width": ""
|
| 292 |
+
}
|
| 293 |
+
},
|
| 294 |
+
"a04d20d2b4934f35a7890f24546023d7": {
|
| 295 |
+
"model_module": "@jupyter-widgets/base",
|
| 296 |
+
"model_name": "LayoutModel",
|
| 297 |
+
"model_module_version": "1.2.0",
|
| 298 |
+
"state": {
|
| 299 |
+
"_model_module": "@jupyter-widgets/base",
|
| 300 |
+
"_model_module_version": "1.2.0",
|
| 301 |
+
"_model_name": "LayoutModel",
|
| 302 |
+
"_view_count": null,
|
| 303 |
+
"_view_module": "@jupyter-widgets/base",
|
| 304 |
+
"_view_module_version": "1.2.0",
|
| 305 |
+
"_view_name": "LayoutView",
|
| 306 |
+
"align_content": null,
|
| 307 |
+
"align_items": null,
|
| 308 |
+
"align_self": null,
|
| 309 |
+
"border": null,
|
| 310 |
+
"bottom": null,
|
| 311 |
+
"display": null,
|
| 312 |
+
"flex": null,
|
| 313 |
+
"flex_flow": null,
|
| 314 |
+
"grid_area": null,
|
| 315 |
+
"grid_auto_columns": null,
|
| 316 |
+
"grid_auto_flow": null,
|
| 317 |
+
"grid_auto_rows": null,
|
| 318 |
+
"grid_column": null,
|
| 319 |
+
"grid_gap": null,
|
| 320 |
+
"grid_row": null,
|
| 321 |
+
"grid_template_areas": null,
|
| 322 |
+
"grid_template_columns": null,
|
| 323 |
+
"grid_template_rows": null,
|
| 324 |
+
"height": null,
|
| 325 |
+
"justify_content": null,
|
| 326 |
+
"justify_items": null,
|
| 327 |
+
"left": null,
|
| 328 |
+
"margin": null,
|
| 329 |
+
"max_height": null,
|
| 330 |
+
"max_width": null,
|
| 331 |
+
"min_height": null,
|
| 332 |
+
"min_width": null,
|
| 333 |
+
"object_fit": null,
|
| 334 |
+
"object_position": null,
|
| 335 |
+
"order": null,
|
| 336 |
+
"overflow": null,
|
| 337 |
+
"overflow_x": null,
|
| 338 |
+
"overflow_y": null,
|
| 339 |
+
"padding": null,
|
| 340 |
+
"right": null,
|
| 341 |
+
"top": null,
|
| 342 |
+
"visibility": null,
|
| 343 |
+
"width": null
|
| 344 |
+
}
|
| 345 |
+
},
|
| 346 |
+
"5f5df2985c6f49d3816888ec4ebd9add": {
|
| 347 |
+
"model_module": "@jupyter-widgets/controls",
|
| 348 |
+
"model_name": "DescriptionStyleModel",
|
| 349 |
+
"model_module_version": "1.5.0",
|
| 350 |
+
"state": {
|
| 351 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 352 |
+
"_model_module_version": "1.5.0",
|
| 353 |
+
"_model_name": "DescriptionStyleModel",
|
| 354 |
+
"_view_count": null,
|
| 355 |
+
"_view_module": "@jupyter-widgets/base",
|
| 356 |
+
"_view_module_version": "1.2.0",
|
| 357 |
+
"_view_name": "StyleView",
|
| 358 |
+
"description_width": ""
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"419e345a9ff34dce965af89ad6569ff1": {
|
| 362 |
+
"model_module": "@jupyter-widgets/controls",
|
| 363 |
+
"model_name": "HBoxModel",
|
| 364 |
+
"model_module_version": "1.5.0",
|
| 365 |
+
"state": {
|
| 366 |
+
"_dom_classes": [],
|
| 367 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 368 |
+
"_model_module_version": "1.5.0",
|
| 369 |
+
"_model_name": "HBoxModel",
|
| 370 |
+
"_view_count": null,
|
| 371 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 372 |
+
"_view_module_version": "1.5.0",
|
| 373 |
+
"_view_name": "HBoxView",
|
| 374 |
+
"box_style": "",
|
| 375 |
+
"children": [
|
| 376 |
+
"IPY_MODEL_2f1473b2871b49f5b916298ab9866bd8",
|
| 377 |
+
"IPY_MODEL_171e066c98944ad2abcad3f61d11144c",
|
| 378 |
+
"IPY_MODEL_67c666a7cc8e4ae5a5c6c7442fdb8484"
|
| 379 |
+
],
|
| 380 |
+
"layout": "IPY_MODEL_3eb3a35b6b2b414fa725a49e002da0e4"
|
| 381 |
+
}
|
| 382 |
+
},
|
| 383 |
+
"2f1473b2871b49f5b916298ab9866bd8": {
|
| 384 |
+
"model_module": "@jupyter-widgets/controls",
|
| 385 |
+
"model_name": "HTMLModel",
|
| 386 |
+
"model_module_version": "1.5.0",
|
| 387 |
+
"state": {
|
| 388 |
+
"_dom_classes": [],
|
| 389 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 390 |
+
"_model_module_version": "1.5.0",
|
| 391 |
+
"_model_name": "HTMLModel",
|
| 392 |
+
"_view_count": null,
|
| 393 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 394 |
+
"_view_module_version": "1.5.0",
|
| 395 |
+
"_view_name": "HTMLView",
|
| 396 |
+
"description": "",
|
| 397 |
+
"description_tooltip": null,
|
| 398 |
+
"layout": "IPY_MODEL_12e03166c7854af59078eb601478338a",
|
| 399 |
+
"placeholder": "",
|
| 400 |
+
"style": "IPY_MODEL_9310394718a64134b5d17290db28f880",
|
| 401 |
+
"value": "Map: 100%"
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"171e066c98944ad2abcad3f61d11144c": {
|
| 405 |
+
"model_module": "@jupyter-widgets/controls",
|
| 406 |
+
"model_name": "FloatProgressModel",
|
| 407 |
+
"model_module_version": "1.5.0",
|
| 408 |
+
"state": {
|
| 409 |
+
"_dom_classes": [],
|
| 410 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 411 |
+
"_model_module_version": "1.5.0",
|
| 412 |
+
"_model_name": "FloatProgressModel",
|
| 413 |
+
"_view_count": null,
|
| 414 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 415 |
+
"_view_module_version": "1.5.0",
|
| 416 |
+
"_view_name": "ProgressView",
|
| 417 |
+
"bar_style": "success",
|
| 418 |
+
"description": "",
|
| 419 |
+
"description_tooltip": null,
|
| 420 |
+
"layout": "IPY_MODEL_c851e5be2363465981fa92285c6a9579",
|
| 421 |
+
"max": 18647,
|
| 422 |
+
"min": 0,
|
| 423 |
+
"orientation": "horizontal",
|
| 424 |
+
"style": "IPY_MODEL_3d2bdb8969cd45499c33a49ab73cab39",
|
| 425 |
+
"value": 18647
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"67c666a7cc8e4ae5a5c6c7442fdb8484": {
|
| 429 |
+
"model_module": "@jupyter-widgets/controls",
|
| 430 |
+
"model_name": "HTMLModel",
|
| 431 |
+
"model_module_version": "1.5.0",
|
| 432 |
+
"state": {
|
| 433 |
+
"_dom_classes": [],
|
| 434 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 435 |
+
"_model_module_version": "1.5.0",
|
| 436 |
+
"_model_name": "HTMLModel",
|
| 437 |
+
"_view_count": null,
|
| 438 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 439 |
+
"_view_module_version": "1.5.0",
|
| 440 |
+
"_view_name": "HTMLView",
|
| 441 |
+
"description": "",
|
| 442 |
+
"description_tooltip": null,
|
| 443 |
+
"layout": "IPY_MODEL_5e584348fea147fb95649323af691ea9",
|
| 444 |
+
"placeholder": "",
|
| 445 |
+
"style": "IPY_MODEL_20af10029189476d8f84badf52743b26",
|
| 446 |
+
"value": " 18647/18647 [00:10<00:00, 1932.89 examples/s]"
|
| 447 |
+
}
|
| 448 |
+
},
|
| 449 |
+
"3eb3a35b6b2b414fa725a49e002da0e4": {
|
| 450 |
+
"model_module": "@jupyter-widgets/base",
|
| 451 |
+
"model_name": "LayoutModel",
|
| 452 |
+
"model_module_version": "1.2.0",
|
| 453 |
+
"state": {
|
| 454 |
+
"_model_module": "@jupyter-widgets/base",
|
| 455 |
+
"_model_module_version": "1.2.0",
|
| 456 |
+
"_model_name": "LayoutModel",
|
| 457 |
+
"_view_count": null,
|
| 458 |
+
"_view_module": "@jupyter-widgets/base",
|
| 459 |
+
"_view_module_version": "1.2.0",
|
| 460 |
+
"_view_name": "LayoutView",
|
| 461 |
+
"align_content": null,
|
| 462 |
+
"align_items": null,
|
| 463 |
+
"align_self": null,
|
| 464 |
+
"border": null,
|
| 465 |
+
"bottom": null,
|
| 466 |
+
"display": null,
|
| 467 |
+
"flex": null,
|
| 468 |
+
"flex_flow": null,
|
| 469 |
+
"grid_area": null,
|
| 470 |
+
"grid_auto_columns": null,
|
| 471 |
+
"grid_auto_flow": null,
|
| 472 |
+
"grid_auto_rows": null,
|
| 473 |
+
"grid_column": null,
|
| 474 |
+
"grid_gap": null,
|
| 475 |
+
"grid_row": null,
|
| 476 |
+
"grid_template_areas": null,
|
| 477 |
+
"grid_template_columns": null,
|
| 478 |
+
"grid_template_rows": null,
|
| 479 |
+
"height": null,
|
| 480 |
+
"justify_content": null,
|
| 481 |
+
"justify_items": null,
|
| 482 |
+
"left": null,
|
| 483 |
+
"margin": null,
|
| 484 |
+
"max_height": null,
|
| 485 |
+
"max_width": null,
|
| 486 |
+
"min_height": null,
|
| 487 |
+
"min_width": null,
|
| 488 |
+
"object_fit": null,
|
| 489 |
+
"object_position": null,
|
| 490 |
+
"order": null,
|
| 491 |
+
"overflow": null,
|
| 492 |
+
"overflow_x": null,
|
| 493 |
+
"overflow_y": null,
|
| 494 |
+
"padding": null,
|
| 495 |
+
"right": null,
|
| 496 |
+
"top": null,
|
| 497 |
+
"visibility": null,
|
| 498 |
+
"width": null
|
| 499 |
+
}
|
| 500 |
+
},
|
| 501 |
+
"12e03166c7854af59078eb601478338a": {
|
| 502 |
+
"model_module": "@jupyter-widgets/base",
|
| 503 |
+
"model_name": "LayoutModel",
|
| 504 |
+
"model_module_version": "1.2.0",
|
| 505 |
+
"state": {
|
| 506 |
+
"_model_module": "@jupyter-widgets/base",
|
| 507 |
+
"_model_module_version": "1.2.0",
|
| 508 |
+
"_model_name": "LayoutModel",
|
| 509 |
+
"_view_count": null,
|
| 510 |
+
"_view_module": "@jupyter-widgets/base",
|
| 511 |
+
"_view_module_version": "1.2.0",
|
| 512 |
+
"_view_name": "LayoutView",
|
| 513 |
+
"align_content": null,
|
| 514 |
+
"align_items": null,
|
| 515 |
+
"align_self": null,
|
| 516 |
+
"border": null,
|
| 517 |
+
"bottom": null,
|
| 518 |
+
"display": null,
|
| 519 |
+
"flex": null,
|
| 520 |
+
"flex_flow": null,
|
| 521 |
+
"grid_area": null,
|
| 522 |
+
"grid_auto_columns": null,
|
| 523 |
+
"grid_auto_flow": null,
|
| 524 |
+
"grid_auto_rows": null,
|
| 525 |
+
"grid_column": null,
|
| 526 |
+
"grid_gap": null,
|
| 527 |
+
"grid_row": null,
|
| 528 |
+
"grid_template_areas": null,
|
| 529 |
+
"grid_template_columns": null,
|
| 530 |
+
"grid_template_rows": null,
|
| 531 |
+
"height": null,
|
| 532 |
+
"justify_content": null,
|
| 533 |
+
"justify_items": null,
|
| 534 |
+
"left": null,
|
| 535 |
+
"margin": null,
|
| 536 |
+
"max_height": null,
|
| 537 |
+
"max_width": null,
|
| 538 |
+
"min_height": null,
|
| 539 |
+
"min_width": null,
|
| 540 |
+
"object_fit": null,
|
| 541 |
+
"object_position": null,
|
| 542 |
+
"order": null,
|
| 543 |
+
"overflow": null,
|
| 544 |
+
"overflow_x": null,
|
| 545 |
+
"overflow_y": null,
|
| 546 |
+
"padding": null,
|
| 547 |
+
"right": null,
|
| 548 |
+
"top": null,
|
| 549 |
+
"visibility": null,
|
| 550 |
+
"width": null
|
| 551 |
+
}
|
| 552 |
+
},
|
| 553 |
+
"9310394718a64134b5d17290db28f880": {
|
| 554 |
+
"model_module": "@jupyter-widgets/controls",
|
| 555 |
+
"model_name": "DescriptionStyleModel",
|
| 556 |
+
"model_module_version": "1.5.0",
|
| 557 |
+
"state": {
|
| 558 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 559 |
+
"_model_module_version": "1.5.0",
|
| 560 |
+
"_model_name": "DescriptionStyleModel",
|
| 561 |
+
"_view_count": null,
|
| 562 |
+
"_view_module": "@jupyter-widgets/base",
|
| 563 |
+
"_view_module_version": "1.2.0",
|
| 564 |
+
"_view_name": "StyleView",
|
| 565 |
+
"description_width": ""
|
| 566 |
+
}
|
| 567 |
+
},
|
| 568 |
+
"c851e5be2363465981fa92285c6a9579": {
|
| 569 |
+
"model_module": "@jupyter-widgets/base",
|
| 570 |
+
"model_name": "LayoutModel",
|
| 571 |
+
"model_module_version": "1.2.0",
|
| 572 |
+
"state": {
|
| 573 |
+
"_model_module": "@jupyter-widgets/base",
|
| 574 |
+
"_model_module_version": "1.2.0",
|
| 575 |
+
"_model_name": "LayoutModel",
|
| 576 |
+
"_view_count": null,
|
| 577 |
+
"_view_module": "@jupyter-widgets/base",
|
| 578 |
+
"_view_module_version": "1.2.0",
|
| 579 |
+
"_view_name": "LayoutView",
|
| 580 |
+
"align_content": null,
|
| 581 |
+
"align_items": null,
|
| 582 |
+
"align_self": null,
|
| 583 |
+
"border": null,
|
| 584 |
+
"bottom": null,
|
| 585 |
+
"display": null,
|
| 586 |
+
"flex": null,
|
| 587 |
+
"flex_flow": null,
|
| 588 |
+
"grid_area": null,
|
| 589 |
+
"grid_auto_columns": null,
|
| 590 |
+
"grid_auto_flow": null,
|
| 591 |
+
"grid_auto_rows": null,
|
| 592 |
+
"grid_column": null,
|
| 593 |
+
"grid_gap": null,
|
| 594 |
+
"grid_row": null,
|
| 595 |
+
"grid_template_areas": null,
|
| 596 |
+
"grid_template_columns": null,
|
| 597 |
+
"grid_template_rows": null,
|
| 598 |
+
"height": null,
|
| 599 |
+
"justify_content": null,
|
| 600 |
+
"justify_items": null,
|
| 601 |
+
"left": null,
|
| 602 |
+
"margin": null,
|
| 603 |
+
"max_height": null,
|
| 604 |
+
"max_width": null,
|
| 605 |
+
"min_height": null,
|
| 606 |
+
"min_width": null,
|
| 607 |
+
"object_fit": null,
|
| 608 |
+
"object_position": null,
|
| 609 |
+
"order": null,
|
| 610 |
+
"overflow": null,
|
| 611 |
+
"overflow_x": null,
|
| 612 |
+
"overflow_y": null,
|
| 613 |
+
"padding": null,
|
| 614 |
+
"right": null,
|
| 615 |
+
"top": null,
|
| 616 |
+
"visibility": null,
|
| 617 |
+
"width": null
|
| 618 |
+
}
|
| 619 |
+
},
|
| 620 |
+
"3d2bdb8969cd45499c33a49ab73cab39": {
|
| 621 |
+
"model_module": "@jupyter-widgets/controls",
|
| 622 |
+
"model_name": "ProgressStyleModel",
|
| 623 |
+
"model_module_version": "1.5.0",
|
| 624 |
+
"state": {
|
| 625 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 626 |
+
"_model_module_version": "1.5.0",
|
| 627 |
+
"_model_name": "ProgressStyleModel",
|
| 628 |
+
"_view_count": null,
|
| 629 |
+
"_view_module": "@jupyter-widgets/base",
|
| 630 |
+
"_view_module_version": "1.2.0",
|
| 631 |
+
"_view_name": "StyleView",
|
| 632 |
+
"bar_color": null,
|
| 633 |
+
"description_width": ""
|
| 634 |
+
}
|
| 635 |
+
},
|
| 636 |
+
"5e584348fea147fb95649323af691ea9": {
|
| 637 |
+
"model_module": "@jupyter-widgets/base",
|
| 638 |
+
"model_name": "LayoutModel",
|
| 639 |
+
"model_module_version": "1.2.0",
|
| 640 |
+
"state": {
|
| 641 |
+
"_model_module": "@jupyter-widgets/base",
|
| 642 |
+
"_model_module_version": "1.2.0",
|
| 643 |
+
"_model_name": "LayoutModel",
|
| 644 |
+
"_view_count": null,
|
| 645 |
+
"_view_module": "@jupyter-widgets/base",
|
| 646 |
+
"_view_module_version": "1.2.0",
|
| 647 |
+
"_view_name": "LayoutView",
|
| 648 |
+
"align_content": null,
|
| 649 |
+
"align_items": null,
|
| 650 |
+
"align_self": null,
|
| 651 |
+
"border": null,
|
| 652 |
+
"bottom": null,
|
| 653 |
+
"display": null,
|
| 654 |
+
"flex": null,
|
| 655 |
+
"flex_flow": null,
|
| 656 |
+
"grid_area": null,
|
| 657 |
+
"grid_auto_columns": null,
|
| 658 |
+
"grid_auto_flow": null,
|
| 659 |
+
"grid_auto_rows": null,
|
| 660 |
+
"grid_column": null,
|
| 661 |
+
"grid_gap": null,
|
| 662 |
+
"grid_row": null,
|
| 663 |
+
"grid_template_areas": null,
|
| 664 |
+
"grid_template_columns": null,
|
| 665 |
+
"grid_template_rows": null,
|
| 666 |
+
"height": null,
|
| 667 |
+
"justify_content": null,
|
| 668 |
+
"justify_items": null,
|
| 669 |
+
"left": null,
|
| 670 |
+
"margin": null,
|
| 671 |
+
"max_height": null,
|
| 672 |
+
"max_width": null,
|
| 673 |
+
"min_height": null,
|
| 674 |
+
"min_width": null,
|
| 675 |
+
"object_fit": null,
|
| 676 |
+
"object_position": null,
|
| 677 |
+
"order": null,
|
| 678 |
+
"overflow": null,
|
| 679 |
+
"overflow_x": null,
|
| 680 |
+
"overflow_y": null,
|
| 681 |
+
"padding": null,
|
| 682 |
+
"right": null,
|
| 683 |
+
"top": null,
|
| 684 |
+
"visibility": null,
|
| 685 |
+
"width": null
|
| 686 |
+
}
|
| 687 |
+
},
|
| 688 |
+
"20af10029189476d8f84badf52743b26": {
|
| 689 |
+
"model_module": "@jupyter-widgets/controls",
|
| 690 |
+
"model_name": "DescriptionStyleModel",
|
| 691 |
+
"model_module_version": "1.5.0",
|
| 692 |
+
"state": {
|
| 693 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 694 |
+
"_model_module_version": "1.5.0",
|
| 695 |
+
"_model_name": "DescriptionStyleModel",
|
| 696 |
+
"_view_count": null,
|
| 697 |
+
"_view_module": "@jupyter-widgets/base",
|
| 698 |
+
"_view_module_version": "1.2.0",
|
| 699 |
+
"_view_name": "StyleView",
|
| 700 |
+
"description_width": ""
|
| 701 |
+
}
|
| 702 |
+
},
|
| 703 |
+
"cc5509c288034ce6939f574301fd5eb2": {
|
| 704 |
+
"model_module": "@jupyter-widgets/controls",
|
| 705 |
+
"model_name": "HBoxModel",
|
| 706 |
+
"model_module_version": "1.5.0",
|
| 707 |
+
"state": {
|
| 708 |
+
"_dom_classes": [],
|
| 709 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 710 |
+
"_model_module_version": "1.5.0",
|
| 711 |
+
"_model_name": "HBoxModel",
|
| 712 |
+
"_view_count": null,
|
| 713 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 714 |
+
"_view_module_version": "1.5.0",
|
| 715 |
+
"_view_name": "HBoxView",
|
| 716 |
+
"box_style": "",
|
| 717 |
+
"children": [
|
| 718 |
+
"IPY_MODEL_6eee983896f948f7919722045b190b01",
|
| 719 |
+
"IPY_MODEL_114a72cf85334713aefd3ee3616ebeb2",
|
| 720 |
+
"IPY_MODEL_4dfd352e599c4676b9871da14e8d75b5"
|
| 721 |
+
],
|
| 722 |
+
"layout": "IPY_MODEL_efa7962c591e4b4bb6c54f008444bb0f"
|
| 723 |
+
}
|
| 724 |
+
},
|
| 725 |
+
"6eee983896f948f7919722045b190b01": {
|
| 726 |
+
"model_module": "@jupyter-widgets/controls",
|
| 727 |
+
"model_name": "HTMLModel",
|
| 728 |
+
"model_module_version": "1.5.0",
|
| 729 |
+
"state": {
|
| 730 |
+
"_dom_classes": [],
|
| 731 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 732 |
+
"_model_module_version": "1.5.0",
|
| 733 |
+
"_model_name": "HTMLModel",
|
| 734 |
+
"_view_count": null,
|
| 735 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 736 |
+
"_view_module_version": "1.5.0",
|
| 737 |
+
"_view_name": "HTMLView",
|
| 738 |
+
"description": "",
|
| 739 |
+
"description_tooltip": null,
|
| 740 |
+
"layout": "IPY_MODEL_0169ffddc6014c2ebf92ee902e198e1a",
|
| 741 |
+
"placeholder": "",
|
| 742 |
+
"style": "IPY_MODEL_0e73212111294bdda9c79b97696aaa48",
|
| 743 |
+
"value": "Downloading builder script: "
|
| 744 |
+
}
|
| 745 |
+
},
|
| 746 |
+
"114a72cf85334713aefd3ee3616ebeb2": {
|
| 747 |
+
"model_module": "@jupyter-widgets/controls",
|
| 748 |
+
"model_name": "FloatProgressModel",
|
| 749 |
+
"model_module_version": "1.5.0",
|
| 750 |
+
"state": {
|
| 751 |
+
"_dom_classes": [],
|
| 752 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 753 |
+
"_model_module_version": "1.5.0",
|
| 754 |
+
"_model_name": "FloatProgressModel",
|
| 755 |
+
"_view_count": null,
|
| 756 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 757 |
+
"_view_module_version": "1.5.0",
|
| 758 |
+
"_view_name": "ProgressView",
|
| 759 |
+
"bar_style": "success",
|
| 760 |
+
"description": "",
|
| 761 |
+
"description_tooltip": null,
|
| 762 |
+
"layout": "IPY_MODEL_6cf0f639236040b9ab8bc84665a1e94a",
|
| 763 |
+
"max": 1,
|
| 764 |
+
"min": 0,
|
| 765 |
+
"orientation": "horizontal",
|
| 766 |
+
"style": "IPY_MODEL_ab1eb221a83e4e7299e5fe1056cbf4b8",
|
| 767 |
+
"value": 1
|
| 768 |
+
}
|
| 769 |
+
},
|
| 770 |
+
"4dfd352e599c4676b9871da14e8d75b5": {
|
| 771 |
+
"model_module": "@jupyter-widgets/controls",
|
| 772 |
+
"model_name": "HTMLModel",
|
| 773 |
+
"model_module_version": "1.5.0",
|
| 774 |
+
"state": {
|
| 775 |
+
"_dom_classes": [],
|
| 776 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 777 |
+
"_model_module_version": "1.5.0",
|
| 778 |
+
"_model_name": "HTMLModel",
|
| 779 |
+
"_view_count": null,
|
| 780 |
+
"_view_module": "@jupyter-widgets/controls",
|
| 781 |
+
"_view_module_version": "1.5.0",
|
| 782 |
+
"_view_name": "HTMLView",
|
| 783 |
+
"description": "",
|
| 784 |
+
"description_tooltip": null,
|
| 785 |
+
"layout": "IPY_MODEL_d13fccbfd59c43f687edb2aa0bdd6145",
|
| 786 |
+
"placeholder": "",
|
| 787 |
+
"style": "IPY_MODEL_06c209127feb497bb2e171d229183f16",
|
| 788 |
+
"value": " 8.15k/? [00:00<00:00, 561kB/s]"
|
| 789 |
+
}
|
| 790 |
+
},
|
| 791 |
+
"efa7962c591e4b4bb6c54f008444bb0f": {
|
| 792 |
+
"model_module": "@jupyter-widgets/base",
|
| 793 |
+
"model_name": "LayoutModel",
|
| 794 |
+
"model_module_version": "1.2.0",
|
| 795 |
+
"state": {
|
| 796 |
+
"_model_module": "@jupyter-widgets/base",
|
| 797 |
+
"_model_module_version": "1.2.0",
|
| 798 |
+
"_model_name": "LayoutModel",
|
| 799 |
+
"_view_count": null,
|
| 800 |
+
"_view_module": "@jupyter-widgets/base",
|
| 801 |
+
"_view_module_version": "1.2.0",
|
| 802 |
+
"_view_name": "LayoutView",
|
| 803 |
+
"align_content": null,
|
| 804 |
+
"align_items": null,
|
| 805 |
+
"align_self": null,
|
| 806 |
+
"border": null,
|
| 807 |
+
"bottom": null,
|
| 808 |
+
"display": null,
|
| 809 |
+
"flex": null,
|
| 810 |
+
"flex_flow": null,
|
| 811 |
+
"grid_area": null,
|
| 812 |
+
"grid_auto_columns": null,
|
| 813 |
+
"grid_auto_flow": null,
|
| 814 |
+
"grid_auto_rows": null,
|
| 815 |
+
"grid_column": null,
|
| 816 |
+
"grid_gap": null,
|
| 817 |
+
"grid_row": null,
|
| 818 |
+
"grid_template_areas": null,
|
| 819 |
+
"grid_template_columns": null,
|
| 820 |
+
"grid_template_rows": null,
|
| 821 |
+
"height": null,
|
| 822 |
+
"justify_content": null,
|
| 823 |
+
"justify_items": null,
|
| 824 |
+
"left": null,
|
| 825 |
+
"margin": null,
|
| 826 |
+
"max_height": null,
|
| 827 |
+
"max_width": null,
|
| 828 |
+
"min_height": null,
|
| 829 |
+
"min_width": null,
|
| 830 |
+
"object_fit": null,
|
| 831 |
+
"object_position": null,
|
| 832 |
+
"order": null,
|
| 833 |
+
"overflow": null,
|
| 834 |
+
"overflow_x": null,
|
| 835 |
+
"overflow_y": null,
|
| 836 |
+
"padding": null,
|
| 837 |
+
"right": null,
|
| 838 |
+
"top": null,
|
| 839 |
+
"visibility": null,
|
| 840 |
+
"width": null
|
| 841 |
+
}
|
| 842 |
+
},
|
| 843 |
+
"0169ffddc6014c2ebf92ee902e198e1a": {
|
| 844 |
+
"model_module": "@jupyter-widgets/base",
|
| 845 |
+
"model_name": "LayoutModel",
|
| 846 |
+
"model_module_version": "1.2.0",
|
| 847 |
+
"state": {
|
| 848 |
+
"_model_module": "@jupyter-widgets/base",
|
| 849 |
+
"_model_module_version": "1.2.0",
|
| 850 |
+
"_model_name": "LayoutModel",
|
| 851 |
+
"_view_count": null,
|
| 852 |
+
"_view_module": "@jupyter-widgets/base",
|
| 853 |
+
"_view_module_version": "1.2.0",
|
| 854 |
+
"_view_name": "LayoutView",
|
| 855 |
+
"align_content": null,
|
| 856 |
+
"align_items": null,
|
| 857 |
+
"align_self": null,
|
| 858 |
+
"border": null,
|
| 859 |
+
"bottom": null,
|
| 860 |
+
"display": null,
|
| 861 |
+
"flex": null,
|
| 862 |
+
"flex_flow": null,
|
| 863 |
+
"grid_area": null,
|
| 864 |
+
"grid_auto_columns": null,
|
| 865 |
+
"grid_auto_flow": null,
|
| 866 |
+
"grid_auto_rows": null,
|
| 867 |
+
"grid_column": null,
|
| 868 |
+
"grid_gap": null,
|
| 869 |
+
"grid_row": null,
|
| 870 |
+
"grid_template_areas": null,
|
| 871 |
+
"grid_template_columns": null,
|
| 872 |
+
"grid_template_rows": null,
|
| 873 |
+
"height": null,
|
| 874 |
+
"justify_content": null,
|
| 875 |
+
"justify_items": null,
|
| 876 |
+
"left": null,
|
| 877 |
+
"margin": null,
|
| 878 |
+
"max_height": null,
|
| 879 |
+
"max_width": null,
|
| 880 |
+
"min_height": null,
|
| 881 |
+
"min_width": null,
|
| 882 |
+
"object_fit": null,
|
| 883 |
+
"object_position": null,
|
| 884 |
+
"order": null,
|
| 885 |
+
"overflow": null,
|
| 886 |
+
"overflow_x": null,
|
| 887 |
+
"overflow_y": null,
|
| 888 |
+
"padding": null,
|
| 889 |
+
"right": null,
|
| 890 |
+
"top": null,
|
| 891 |
+
"visibility": null,
|
| 892 |
+
"width": null
|
| 893 |
+
}
|
| 894 |
+
},
|
| 895 |
+
"0e73212111294bdda9c79b97696aaa48": {
|
| 896 |
+
"model_module": "@jupyter-widgets/controls",
|
| 897 |
+
"model_name": "DescriptionStyleModel",
|
| 898 |
+
"model_module_version": "1.5.0",
|
| 899 |
+
"state": {
|
| 900 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 901 |
+
"_model_module_version": "1.5.0",
|
| 902 |
+
"_model_name": "DescriptionStyleModel",
|
| 903 |
+
"_view_count": null,
|
| 904 |
+
"_view_module": "@jupyter-widgets/base",
|
| 905 |
+
"_view_module_version": "1.2.0",
|
| 906 |
+
"_view_name": "StyleView",
|
| 907 |
+
"description_width": ""
|
| 908 |
+
}
|
| 909 |
+
},
|
| 910 |
+
"6cf0f639236040b9ab8bc84665a1e94a": {
|
| 911 |
+
"model_module": "@jupyter-widgets/base",
|
| 912 |
+
"model_name": "LayoutModel",
|
| 913 |
+
"model_module_version": "1.2.0",
|
| 914 |
+
"state": {
|
| 915 |
+
"_model_module": "@jupyter-widgets/base",
|
| 916 |
+
"_model_module_version": "1.2.0",
|
| 917 |
+
"_model_name": "LayoutModel",
|
| 918 |
+
"_view_count": null,
|
| 919 |
+
"_view_module": "@jupyter-widgets/base",
|
| 920 |
+
"_view_module_version": "1.2.0",
|
| 921 |
+
"_view_name": "LayoutView",
|
| 922 |
+
"align_content": null,
|
| 923 |
+
"align_items": null,
|
| 924 |
+
"align_self": null,
|
| 925 |
+
"border": null,
|
| 926 |
+
"bottom": null,
|
| 927 |
+
"display": null,
|
| 928 |
+
"flex": null,
|
| 929 |
+
"flex_flow": null,
|
| 930 |
+
"grid_area": null,
|
| 931 |
+
"grid_auto_columns": null,
|
| 932 |
+
"grid_auto_flow": null,
|
| 933 |
+
"grid_auto_rows": null,
|
| 934 |
+
"grid_column": null,
|
| 935 |
+
"grid_gap": null,
|
| 936 |
+
"grid_row": null,
|
| 937 |
+
"grid_template_areas": null,
|
| 938 |
+
"grid_template_columns": null,
|
| 939 |
+
"grid_template_rows": null,
|
| 940 |
+
"height": null,
|
| 941 |
+
"justify_content": null,
|
| 942 |
+
"justify_items": null,
|
| 943 |
+
"left": null,
|
| 944 |
+
"margin": null,
|
| 945 |
+
"max_height": null,
|
| 946 |
+
"max_width": null,
|
| 947 |
+
"min_height": null,
|
| 948 |
+
"min_width": null,
|
| 949 |
+
"object_fit": null,
|
| 950 |
+
"object_position": null,
|
| 951 |
+
"order": null,
|
| 952 |
+
"overflow": null,
|
| 953 |
+
"overflow_x": null,
|
| 954 |
+
"overflow_y": null,
|
| 955 |
+
"padding": null,
|
| 956 |
+
"right": null,
|
| 957 |
+
"top": null,
|
| 958 |
+
"visibility": null,
|
| 959 |
+
"width": "20px"
|
| 960 |
+
}
|
| 961 |
+
},
|
| 962 |
+
"ab1eb221a83e4e7299e5fe1056cbf4b8": {
|
| 963 |
+
"model_module": "@jupyter-widgets/controls",
|
| 964 |
+
"model_name": "ProgressStyleModel",
|
| 965 |
+
"model_module_version": "1.5.0",
|
| 966 |
+
"state": {
|
| 967 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 968 |
+
"_model_module_version": "1.5.0",
|
| 969 |
+
"_model_name": "ProgressStyleModel",
|
| 970 |
+
"_view_count": null,
|
| 971 |
+
"_view_module": "@jupyter-widgets/base",
|
| 972 |
+
"_view_module_version": "1.2.0",
|
| 973 |
+
"_view_name": "StyleView",
|
| 974 |
+
"bar_color": null,
|
| 975 |
+
"description_width": ""
|
| 976 |
+
}
|
| 977 |
+
},
|
| 978 |
+
"d13fccbfd59c43f687edb2aa0bdd6145": {
|
| 979 |
+
"model_module": "@jupyter-widgets/base",
|
| 980 |
+
"model_name": "LayoutModel",
|
| 981 |
+
"model_module_version": "1.2.0",
|
| 982 |
+
"state": {
|
| 983 |
+
"_model_module": "@jupyter-widgets/base",
|
| 984 |
+
"_model_module_version": "1.2.0",
|
| 985 |
+
"_model_name": "LayoutModel",
|
| 986 |
+
"_view_count": null,
|
| 987 |
+
"_view_module": "@jupyter-widgets/base",
|
| 988 |
+
"_view_module_version": "1.2.0",
|
| 989 |
+
"_view_name": "LayoutView",
|
| 990 |
+
"align_content": null,
|
| 991 |
+
"align_items": null,
|
| 992 |
+
"align_self": null,
|
| 993 |
+
"border": null,
|
| 994 |
+
"bottom": null,
|
| 995 |
+
"display": null,
|
| 996 |
+
"flex": null,
|
| 997 |
+
"flex_flow": null,
|
| 998 |
+
"grid_area": null,
|
| 999 |
+
"grid_auto_columns": null,
|
| 1000 |
+
"grid_auto_flow": null,
|
| 1001 |
+
"grid_auto_rows": null,
|
| 1002 |
+
"grid_column": null,
|
| 1003 |
+
"grid_gap": null,
|
| 1004 |
+
"grid_row": null,
|
| 1005 |
+
"grid_template_areas": null,
|
| 1006 |
+
"grid_template_columns": null,
|
| 1007 |
+
"grid_template_rows": null,
|
| 1008 |
+
"height": null,
|
| 1009 |
+
"justify_content": null,
|
| 1010 |
+
"justify_items": null,
|
| 1011 |
+
"left": null,
|
| 1012 |
+
"margin": null,
|
| 1013 |
+
"max_height": null,
|
| 1014 |
+
"max_width": null,
|
| 1015 |
+
"min_height": null,
|
| 1016 |
+
"min_width": null,
|
| 1017 |
+
"object_fit": null,
|
| 1018 |
+
"object_position": null,
|
| 1019 |
+
"order": null,
|
| 1020 |
+
"overflow": null,
|
| 1021 |
+
"overflow_x": null,
|
| 1022 |
+
"overflow_y": null,
|
| 1023 |
+
"padding": null,
|
| 1024 |
+
"right": null,
|
| 1025 |
+
"top": null,
|
| 1026 |
+
"visibility": null,
|
| 1027 |
+
"width": null
|
| 1028 |
+
}
|
| 1029 |
+
},
|
| 1030 |
+
"06c209127feb497bb2e171d229183f16": {
|
| 1031 |
+
"model_module": "@jupyter-widgets/controls",
|
| 1032 |
+
"model_name": "DescriptionStyleModel",
|
| 1033 |
+
"model_module_version": "1.5.0",
|
| 1034 |
+
"state": {
|
| 1035 |
+
"_model_module": "@jupyter-widgets/controls",
|
| 1036 |
+
"_model_module_version": "1.5.0",
|
| 1037 |
+
"_model_name": "DescriptionStyleModel",
|
| 1038 |
+
"_view_count": null,
|
| 1039 |
+
"_view_module": "@jupyter-widgets/base",
|
| 1040 |
+
"_view_module_version": "1.2.0",
|
| 1041 |
+
"_view_name": "StyleView",
|
| 1042 |
+
"description_width": ""
|
| 1043 |
+
}
|
| 1044 |
+
}
|
| 1045 |
+
}
|
| 1046 |
+
}
|
| 1047 |
+
},
|
| 1048 |
+
"cells": [
|
| 1049 |
+
{
|
| 1050 |
+
"cell_type": "markdown",
|
| 1051 |
+
"metadata": {
|
| 1052 |
+
"id": "view-in-github"
|
| 1053 |
+
},
|
| 1054 |
+
"source": [
|
| 1055 |
+
"<a href=\"https://colab.research.google.com/github/your-username/mt5-finetune-en-de/blob/main/mt5_finetune_en_de.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
| 1056 |
+
]
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"cell_type": "markdown",
|
| 1060 |
+
"source": [
|
| 1061 |
+
"# Fine-Tuning mT5 for English → German Translation\n",
|
| 1062 |
+
"\n",
|
| 1063 |
+
"This notebook fine-tunes **`google/mt5-small`** on the **WMT16 En→De** dataset using Hugging Face Transformers.\n",
|
| 1064 |
+
"\n",
|
| 1065 |
+
"- Model: Multilingual T5 (mT5) – pre-trained on 101 languages **without supervised translation**\n",
|
| 1066 |
+
"- Task: Teach it **high-quality English to German translation** via fine-tuning\n",
|
| 1067 |
+
"- Dataset: WMT16 (via `datasets` library)\n",
|
| 1068 |
+
"- Framework: `transformers` + `seq2seq` Trainer\n",
|
| 1069 |
+
"\n",
|
| 1070 |
+
"---"
|
| 1071 |
+
],
|
| 1072 |
+
"metadata": {
|
| 1073 |
+
"id": "XnxaVxCe8gjQ"
|
| 1074 |
+
}
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"cell_type": "markdown",
|
| 1078 |
+
"source": [
|
| 1079 |
+
"## 1. Install Dependencies"
|
| 1080 |
+
],
|
| 1081 |
+
"metadata": {
|
| 1082 |
+
"id": "P05w2JE68gjR"
|
| 1083 |
+
}
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"cell_type": "code",
|
| 1087 |
+
"source": [
|
| 1088 |
+
"from google.colab import drive\n",
|
| 1089 |
+
"drive.mount('/content/drive')\n"
|
| 1090 |
+
],
|
| 1091 |
+
"metadata": {
|
| 1092 |
+
"colab": {
|
| 1093 |
+
"base_uri": "https://localhost:8080/"
|
| 1094 |
+
},
|
| 1095 |
+
"id": "3-EOS45xALKJ",
|
| 1096 |
+
"outputId": "7b790ea5-c852-4688-9189-91a725c6be72"
|
| 1097 |
+
},
|
| 1098 |
+
"execution_count": 1,
|
| 1099 |
+
"outputs": [
|
| 1100 |
+
{
|
| 1101 |
+
"output_type": "stream",
|
| 1102 |
+
"name": "stdout",
|
| 1103 |
+
"text": [
|
| 1104 |
+
"Mounted at /content/drive\n"
|
| 1105 |
+
]
|
| 1106 |
+
}
|
| 1107 |
+
]
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"cell_type": "code",
|
| 1111 |
+
"execution_count": 2,
|
| 1112 |
+
"outputs": [
|
| 1113 |
+
{
|
| 1114 |
+
"output_type": "stream",
|
| 1115 |
+
"name": "stdout",
|
| 1116 |
+
"text": [
|
| 1117 |
+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.8/51.8 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
| 1118 |
+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.1/104.1 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
| 1119 |
+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
| 1120 |
+
"\u001b[?25h"
|
| 1121 |
+
]
|
| 1122 |
+
}
|
| 1123 |
+
],
|
| 1124 |
+
"source": [
|
| 1125 |
+
"!pip install -q transformers datasets sentencepiece sacrebleu accelerate evaluate\n",
|
| 1126 |
+
"!pip install -q torch --index-url https://download.pytorch.org/whl/cu118"
|
| 1127 |
+
],
|
| 1128 |
+
"metadata": {
|
| 1129 |
+
"colab": {
|
| 1130 |
+
"base_uri": "https://localhost:8080/"
|
| 1131 |
+
},
|
| 1132 |
+
"id": "tBzChq5L8gjR",
|
| 1133 |
+
"outputId": "264ac5a0-a9ef-4f49-a5be-6045a15181f6"
|
| 1134 |
+
}
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"cell_type": "code",
|
| 1138 |
+
"source": [
|
| 1139 |
+
"!pip install pandas"
|
| 1140 |
+
],
|
| 1141 |
+
"metadata": {
|
| 1142 |
+
"colab": {
|
| 1143 |
+
"base_uri": "https://localhost:8080/"
|
| 1144 |
+
},
|
| 1145 |
+
"id": "1O0iGKJ7A6yW",
|
| 1146 |
+
"outputId": "4194b26b-9090-4444-866f-b86e7058179b"
|
| 1147 |
+
},
|
| 1148 |
+
"execution_count": 5,
|
| 1149 |
+
"outputs": [
|
| 1150 |
+
{
|
| 1151 |
+
"output_type": "stream",
|
| 1152 |
+
"name": "stdout",
|
| 1153 |
+
"text": [
|
| 1154 |
+
"Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
|
| 1155 |
+
"Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.0.2)\n",
|
| 1156 |
+
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
|
| 1157 |
+
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
|
| 1158 |
+
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
|
| 1159 |
+
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
|
| 1160 |
+
]
|
| 1161 |
+
}
|
| 1162 |
+
]
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"cell_type": "markdown",
|
| 1166 |
+
"source": [
|
| 1167 |
+
"## 2. Load Dataset (WMT16 En→De)"
|
| 1168 |
+
],
|
| 1169 |
+
"metadata": {
|
| 1170 |
+
"id": "_niqDW2e8gjS"
|
| 1171 |
+
}
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"cell_type": "code",
|
| 1175 |
+
"source": [
|
| 1176 |
+
"import gdown\n",
|
| 1177 |
+
"import json\n",
|
| 1178 |
+
"\n",
|
| 1179 |
+
"data_path = \"/content/drive/MyDrive/llm-translator/parallel_corpus.json\" # Adjust path\n",
|
| 1180 |
+
"try:\n",
|
| 1181 |
+
" with open(data_path, \"r\", encoding=\"utf-8\") as file:\n",
|
| 1182 |
+
" data = json.load(file)\n",
|
| 1183 |
+
" print(f\"Loaded {len(data)} entries from parallel_corpus.json\")\n",
|
| 1184 |
+
"except FileNotFoundError:\n",
|
| 1185 |
+
" print(f\"Error: The file '{data_path}' was not found.\")\n",
|
| 1186 |
+
" exit(1)\n",
|
| 1187 |
+
"except json.JSONDecodeError:\n",
|
| 1188 |
+
" print(\"Error: Failed to decode JSON from the file.\")\n",
|
| 1189 |
+
" exit(1)"
|
| 1190 |
+
],
|
| 1191 |
+
"metadata": {
|
| 1192 |
+
"colab": {
|
| 1193 |
+
"base_uri": "https://localhost:8080/"
|
| 1194 |
+
},
|
| 1195 |
+
"id": "ds1obOiM8gjT",
|
| 1196 |
+
"outputId": "25f14e99-d3fb-491b-c9c8-7807e8d2b6f5"
|
| 1197 |
+
},
|
| 1198 |
+
"execution_count": 3,
|
| 1199 |
+
"outputs": [
|
| 1200 |
+
{
|
| 1201 |
+
"output_type": "stream",
|
| 1202 |
+
"name": "stdout",
|
| 1203 |
+
"text": [
|
| 1204 |
+
"Loaded 31192 entries from parallel_corpus.json\n"
|
| 1205 |
+
]
|
| 1206 |
+
}
|
| 1207 |
+
]
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"cell_type": "code",
|
| 1211 |
+
"source": [
|
| 1212 |
+
"import string\n",
|
| 1213 |
+
"import pandas as pd\n",
|
| 1214 |
+
"from datasets import Dataset, DatasetDict\n",
|
| 1215 |
+
"\n",
|
| 1216 |
+
"\n",
|
| 1217 |
+
"# Build the three language pairs exactly as you did\n",
|
| 1218 |
+
"def is_valid(t): return bool(t and t.strip() and t.strip() not in string.punctuation)\n",
|
| 1219 |
+
"df = pd.DataFrame(data)\n",
|
| 1220 |
+
"breton_df = df[df.apply(lambda r: is_valid(r[\"niv_text\"]) and is_valid(r[\"koad21_text\"]), axis=1)][[\"niv_text\",\"koad21_text\"]].rename(columns={\"niv_text\":\"en\",\"koad21_text\":\"target\"})\n",
|
| 1221 |
+
"breton_df[\"language\"] = \"br\"\n",
|
| 1222 |
+
"cornish_df = df[df.apply(lambda r: is_valid(r[\"niv_text\"]) and is_valid(r[\"abk_text\"]), axis=1)][[\"niv_text\",\"abk_text\"]].rename(columns={\"niv_text\":\"en\",\"abk_text\":\"target\"})\n",
|
| 1223 |
+
"cornish_df[\"language\"] = \"abk\"\n",
|
| 1224 |
+
"welsh_df = df[df.apply(lambda r: is_valid(r[\"niv_text\"]) and is_valid(r[\"bcnda_text\"]), axis=1)][[\"niv_text\",\"bcnda_text\"]].rename(columns={\"niv_text\":\"en\",\"bcnda_text\":\"target\"})\n",
|
| 1225 |
+
"welsh_df[\"language\"] = \"cy\"\n",
|
| 1226 |
+
"\n",
|
| 1227 |
+
"\n",
|
| 1228 |
+
"combined_df = pd.concat([breton_df, cornish_df, welsh_df], ignore_index=True)\n",
|
| 1229 |
+
"print(combined_df.head(5))\n",
|
| 1230 |
+
"dataset = Dataset.from_pandas(combined_df).train_test_split(test_size=0.2, seed=42)\n",
|
| 1231 |
+
"print(f\"Combined dataset size: {len(combined_df)} pairs (Breton: {len(breton_df)}, Cornish: {len(cornish_df)}, Welsh: {len(welsh_df)})\")\n",
|
| 1232 |
+
"\n",
|
| 1233 |
+
"raw_datasets = DatasetDict({\n",
|
| 1234 |
+
" \"train\": dataset[\"train\"],\n",
|
| 1235 |
+
" \"test\" : dataset[\"test\"]\n",
|
| 1236 |
+
"})\n",
|
| 1237 |
+
"print(f\"Train: {len(raw_datasets['train'])}, Test: {len(raw_datasets['test'])}\")\n",
|
| 1238 |
+
"print(raw_datasets['train'])"
|
| 1239 |
+
],
|
| 1240 |
+
"metadata": {
|
| 1241 |
+
"colab": {
|
| 1242 |
+
"base_uri": "https://localhost:8080/"
|
| 1243 |
+
},
|
| 1244 |
+
"id": "jbv3mVHMAdZT",
|
| 1245 |
+
"outputId": "f42a3f59-4be9-46f3-fc9d-80f4614cbf3f"
|
| 1246 |
+
},
|
| 1247 |
+
"execution_count": 10,
|
| 1248 |
+
"outputs": [
|
| 1249 |
+
{
|
| 1250 |
+
"output_type": "stream",
|
| 1251 |
+
"name": "stdout",
|
| 1252 |
+
"text": [
|
| 1253 |
+
" en \\\n",
|
| 1254 |
+
"0 The Lord called to Moses and spoke to him from... \n",
|
| 1255 |
+
"1 “Speak to the Israelites and say to them: ‘Whe... \n",
|
| 1256 |
+
"2 “ ‘If the offering is a burnt offering from th... \n",
|
| 1257 |
+
"3 You are to lay your hand on the head of the bu... \n",
|
| 1258 |
+
"4 You are to slaughter the young bull before the... \n",
|
| 1259 |
+
"\n",
|
| 1260 |
+
" target language \n",
|
| 1261 |
+
"0 An AOTROU a c’halvas Moizez hag a gomzas dezha... br \n",
|
| 1262 |
+
"1 Komz da vibien Israel ha lavar: Pa raio unan b... br \n",
|
| 1263 |
+
"2 Mar d-eo e brof ul loskaberzh a loened bras, e... br \n",
|
| 1264 |
+
"3 Lakaat a raio e zorn war benn al loskaberzh, a... br \n",
|
| 1265 |
+
"4 Lazhañ a raio ar c’hole dirak an AOTROU ; an a... br \n",
|
| 1266 |
+
"Combined dataset size: 93233 pairs (Breton: 31077, Cornish: 31086, Welsh: 31070)\n",
|
| 1267 |
+
"Train: 74586, Test: 18647\n",
|
| 1268 |
+
"Dataset({\n",
|
| 1269 |
+
" features: ['en', 'target', 'language'],\n",
|
| 1270 |
+
" num_rows: 74586\n",
|
| 1271 |
+
"})\n"
|
| 1272 |
+
]
|
| 1273 |
+
}
|
| 1274 |
+
]
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"cell_type": "markdown",
|
| 1278 |
+
"source": [
|
| 1279 |
+
"## 3. Load Model & Tokenizer"
|
| 1280 |
+
],
|
| 1281 |
+
"metadata": {
|
| 1282 |
+
"id": "920INjs88gjT"
|
| 1283 |
+
}
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"cell_type": "code",
|
| 1287 |
+
"source": [
|
| 1288 |
+
"from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
|
| 1289 |
+
"\n",
|
| 1290 |
+
"model_name = \"t5-small\"\n",
|
| 1291 |
+
"tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)\n",
|
| 1292 |
+
"model = AutoModelForSeq2SeqLM.from_pretrained(model_name)\n",
|
| 1293 |
+
"\n",
|
| 1294 |
+
"# mT5 uses SentencePiece – no fast tokenizer available"
|
| 1295 |
+
],
|
| 1296 |
+
"metadata": {
|
| 1297 |
+
"id": "7XvJ2Sl38gjT"
|
| 1298 |
+
},
|
| 1299 |
+
"execution_count": 11,
|
| 1300 |
+
"outputs": []
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"cell_type": "markdown",
|
| 1304 |
+
"source": [
|
| 1305 |
+
"## 4. Preprocess Function"
|
| 1306 |
+
],
|
| 1307 |
+
"metadata": {
|
| 1308 |
+
"id": "H-cPZfJj8gjU"
|
| 1309 |
+
}
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"cell_type": "code",
|
| 1313 |
+
"source": [
|
| 1314 |
+
"max_input_length = 128\n",
|
| 1315 |
+
"max_target_length = 128\n",
|
| 1316 |
+
"\n",
|
| 1317 |
+
"def preprocess(examples):\n",
|
| 1318 |
+
" inputs = [f\"translate English to {lang}: {en}\"\n",
|
| 1319 |
+
" for lang, en in zip(examples[\"language\"], examples[\"en\"])]\n",
|
| 1320 |
+
" targets = examples[\"target\"]\n",
|
| 1321 |
+
" model_inputs = tokenizer(inputs, max_length=max_input_length,\n",
|
| 1322 |
+
" truncation=True, padding=\"max_length\")\n",
|
| 1323 |
+
" labels = tokenizer(targets, max_length=max_target_length,\n",
|
| 1324 |
+
" truncation=True, padding=\"max_length\").input_ids\n",
|
| 1325 |
+
" model_inputs[\"labels\"] = labels\n",
|
| 1326 |
+
" return model_inputs\n",
|
| 1327 |
+
"\n"
|
| 1328 |
+
],
|
| 1329 |
+
"metadata": {
|
| 1330 |
+
"id": "eY7-UjaE8gjU"
|
| 1331 |
+
},
|
| 1332 |
+
"execution_count": 13,
|
| 1333 |
+
"outputs": []
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"cell_type": "code",
|
| 1337 |
+
"source": [
|
| 1338 |
+
"# Apply preprocessing\n",
|
| 1339 |
+
"print(\"Tokenising …\")\n",
|
| 1340 |
+
"print(raw_datasets)\n",
|
| 1341 |
+
"tokenized_datasets = raw_datasets.map(preprocess,\n",
|
| 1342 |
+
" batched=True,\n",
|
| 1343 |
+
" remove_columns=raw_datasets[\"train\"].column_names)\n",
|
| 1344 |
+
"\n",
|
| 1345 |
+
"print(tokenized_datasets)"
|
| 1346 |
+
],
|
| 1347 |
+
"metadata": {
|
| 1348 |
+
"colab": {
|
| 1349 |
+
"base_uri": "https://localhost:8080/",
|
| 1350 |
+
"height": 456,
|
| 1351 |
+
"referenced_widgets": [
|
| 1352 |
+
"8a49fb7918744d23bf64237c2674fc6b",
|
| 1353 |
+
"7a64e72d88084b6897d53c344aad4358",
|
| 1354 |
+
"85b34cfea65c4a8dbdae30a8eec22a98",
|
| 1355 |
+
"500b7fb2607c4eebbb5bea0bfc4e33ff",
|
| 1356 |
+
"b53f4a68898e45098d6801e4987e4c10",
|
| 1357 |
+
"008567f59c13464b82ca3946ccf0058c",
|
| 1358 |
+
"6ac91c5649bc4b6fa0d3860e71cdb01b",
|
| 1359 |
+
"90bfdbd03ac44d5ca3df23ebcc02d863",
|
| 1360 |
+
"6618b65302df46098bd2ad029ed668eb",
|
| 1361 |
+
"a04d20d2b4934f35a7890f24546023d7",
|
| 1362 |
+
"5f5df2985c6f49d3816888ec4ebd9add",
|
| 1363 |
+
"419e345a9ff34dce965af89ad6569ff1",
|
| 1364 |
+
"2f1473b2871b49f5b916298ab9866bd8",
|
| 1365 |
+
"171e066c98944ad2abcad3f61d11144c",
|
| 1366 |
+
"67c666a7cc8e4ae5a5c6c7442fdb8484",
|
| 1367 |
+
"3eb3a35b6b2b414fa725a49e002da0e4",
|
| 1368 |
+
"12e03166c7854af59078eb601478338a",
|
| 1369 |
+
"9310394718a64134b5d17290db28f880",
|
| 1370 |
+
"c851e5be2363465981fa92285c6a9579",
|
| 1371 |
+
"3d2bdb8969cd45499c33a49ab73cab39",
|
| 1372 |
+
"5e584348fea147fb95649323af691ea9",
|
| 1373 |
+
"20af10029189476d8f84badf52743b26"
|
| 1374 |
+
]
|
| 1375 |
+
},
|
| 1376 |
+
"id": "HVO9qHXZ8gjV",
|
| 1377 |
+
"outputId": "0a5edd95-149e-4596-abc3-2668b500f7b1"
|
| 1378 |
+
},
|
| 1379 |
+
"execution_count": 14,
|
| 1380 |
+
"outputs": [
|
| 1381 |
+
{
|
| 1382 |
+
"output_type": "stream",
|
| 1383 |
+
"name": "stdout",
|
| 1384 |
+
"text": [
|
| 1385 |
+
"Tokenising …\n",
|
| 1386 |
+
"DatasetDict({\n",
|
| 1387 |
+
" train: Dataset({\n",
|
| 1388 |
+
" features: ['en', 'target', 'language'],\n",
|
| 1389 |
+
" num_rows: 74586\n",
|
| 1390 |
+
" })\n",
|
| 1391 |
+
" test: Dataset({\n",
|
| 1392 |
+
" features: ['en', 'target', 'language'],\n",
|
| 1393 |
+
" num_rows: 18647\n",
|
| 1394 |
+
" })\n",
|
| 1395 |
+
"})\n"
|
| 1396 |
+
]
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"output_type": "display_data",
|
| 1400 |
+
"data": {
|
| 1401 |
+
"text/plain": [
|
| 1402 |
+
"Map: 0%| | 0/74586 [00:00<?, ? examples/s]"
|
| 1403 |
+
],
|
| 1404 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 1405 |
+
"version_major": 2,
|
| 1406 |
+
"version_minor": 0,
|
| 1407 |
+
"model_id": "8a49fb7918744d23bf64237c2674fc6b"
|
| 1408 |
+
}
|
| 1409 |
+
},
|
| 1410 |
+
"metadata": {}
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"output_type": "display_data",
|
| 1414 |
+
"data": {
|
| 1415 |
+
"text/plain": [
|
| 1416 |
+
"Map: 0%| | 0/18647 [00:00<?, ? examples/s]"
|
| 1417 |
+
],
|
| 1418 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 1419 |
+
"version_major": 2,
|
| 1420 |
+
"version_minor": 0,
|
| 1421 |
+
"model_id": "419e345a9ff34dce965af89ad6569ff1"
|
| 1422 |
+
}
|
| 1423 |
+
},
|
| 1424 |
+
"metadata": {}
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"output_type": "stream",
|
| 1428 |
+
"name": "stdout",
|
| 1429 |
+
"text": [
|
| 1430 |
+
"DatasetDict({\n",
|
| 1431 |
+
" train: Dataset({\n",
|
| 1432 |
+
" features: ['input_ids', 'attention_mask', 'labels'],\n",
|
| 1433 |
+
" num_rows: 74586\n",
|
| 1434 |
+
" })\n",
|
| 1435 |
+
" test: Dataset({\n",
|
| 1436 |
+
" features: ['input_ids', 'attention_mask', 'labels'],\n",
|
| 1437 |
+
" num_rows: 18647\n",
|
| 1438 |
+
" })\n",
|
| 1439 |
+
"})\n"
|
| 1440 |
+
]
|
| 1441 |
+
}
|
| 1442 |
+
]
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"cell_type": "markdown",
|
| 1446 |
+
"source": [
|
| 1447 |
+
"## 5. Data Collator"
|
| 1448 |
+
],
|
| 1449 |
+
"metadata": {
|
| 1450 |
+
"id": "TynYzUyG8gjV"
|
| 1451 |
+
}
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"cell_type": "code",
|
| 1455 |
+
"source": [
|
| 1456 |
+
"from transformers import DataCollatorForSeq2Seq\n",
|
| 1457 |
+
"\n",
|
| 1458 |
+
"data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)"
|
| 1459 |
+
],
|
| 1460 |
+
"metadata": {
|
| 1461 |
+
"id": "CAumdmQH8gjV"
|
| 1462 |
+
},
|
| 1463 |
+
"execution_count": 15,
|
| 1464 |
+
"outputs": []
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"cell_type": "markdown",
|
| 1468 |
+
"source": [
|
| 1469 |
+
"## 6. Evaluation Metric (BLEU)"
|
| 1470 |
+
],
|
| 1471 |
+
"metadata": {
|
| 1472 |
+
"id": "4CO7Ribv8gjV"
|
| 1473 |
+
}
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"cell_type": "code",
|
| 1477 |
+
"source": [
|
| 1478 |
+
"import evaluate\n",
|
| 1479 |
+
"import numpy as np\n",
|
| 1480 |
+
"\n",
|
| 1481 |
+
"metric = evaluate.load(\"sacrebleu\")\n",
|
| 1482 |
+
"\n",
|
| 1483 |
+
"def postprocess_text(preds, labels):\n",
|
| 1484 |
+
" preds = [pred.strip() for pred in preds]\n",
|
| 1485 |
+
" labels = [[label.strip()] for label in labels]\n",
|
| 1486 |
+
" return preds, labels\n",
|
| 1487 |
+
"\n",
|
| 1488 |
+
"def compute_metrics(eval_preds):\n",
|
| 1489 |
+
" preds, labels = eval_preds\n",
|
| 1490 |
+
" if isinstance(preds, tuple):\n",
|
| 1491 |
+
" preds = preds[0]\n",
|
| 1492 |
+
" decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)\n",
|
| 1493 |
+
"\n",
|
| 1494 |
+
" # Replace -100 in the labels as we can't decode them\n",
|
| 1495 |
+
" labels = np.where(labels != -100, labels, tokenizer.pad_token_id)\n",
|
| 1496 |
+
" decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)\n",
|
| 1497 |
+
"\n",
|
| 1498 |
+
" decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)\n",
|
| 1499 |
+
"\n",
|
| 1500 |
+
" result = metric.compute(predictions=decoded_preds, references=decoded_labels)\n",
|
| 1501 |
+
" result = {\"bleu\": result[\"score\"]}\n",
|
| 1502 |
+
"\n",
|
| 1503 |
+
" return result"
|
| 1504 |
+
],
|
| 1505 |
+
"metadata": {
|
| 1506 |
+
"colab": {
|
| 1507 |
+
"base_uri": "https://localhost:8080/",
|
| 1508 |
+
"height": 49,
|
| 1509 |
+
"referenced_widgets": [
|
| 1510 |
+
"cc5509c288034ce6939f574301fd5eb2",
|
| 1511 |
+
"6eee983896f948f7919722045b190b01",
|
| 1512 |
+
"114a72cf85334713aefd3ee3616ebeb2",
|
| 1513 |
+
"4dfd352e599c4676b9871da14e8d75b5",
|
| 1514 |
+
"efa7962c591e4b4bb6c54f008444bb0f",
|
| 1515 |
+
"0169ffddc6014c2ebf92ee902e198e1a",
|
| 1516 |
+
"0e73212111294bdda9c79b97696aaa48",
|
| 1517 |
+
"6cf0f639236040b9ab8bc84665a1e94a",
|
| 1518 |
+
"ab1eb221a83e4e7299e5fe1056cbf4b8",
|
| 1519 |
+
"d13fccbfd59c43f687edb2aa0bdd6145",
|
| 1520 |
+
"06c209127feb497bb2e171d229183f16"
|
| 1521 |
+
]
|
| 1522 |
+
},
|
| 1523 |
+
"id": "KoUWoPjQ8gjV",
|
| 1524 |
+
"outputId": "efd48518-f5a0-463a-ad3e-86ea3b856c4f"
|
| 1525 |
+
},
|
| 1526 |
+
"execution_count": 16,
|
| 1527 |
+
"outputs": [
|
| 1528 |
+
{
|
| 1529 |
+
"output_type": "display_data",
|
| 1530 |
+
"data": {
|
| 1531 |
+
"text/plain": [
|
| 1532 |
+
"Downloading builder script: 0.00B [00:00, ?B/s]"
|
| 1533 |
+
],
|
| 1534 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 1535 |
+
"version_major": 2,
|
| 1536 |
+
"version_minor": 0,
|
| 1537 |
+
"model_id": "cc5509c288034ce6939f574301fd5eb2"
|
| 1538 |
+
}
|
| 1539 |
+
},
|
| 1540 |
+
"metadata": {}
|
| 1541 |
+
}
|
| 1542 |
+
]
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"cell_type": "markdown",
|
| 1546 |
+
"source": [
|
| 1547 |
+
"## 7. Training Setup"
|
| 1548 |
+
],
|
| 1549 |
+
"metadata": {
|
| 1550 |
+
"id": "2B_-jhu58gjV"
|
| 1551 |
+
}
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"cell_type": "code",
|
| 1555 |
+
"source": [
|
| 1556 |
+
"from transformers import Seq2SeqTrainingArguments, Seq2SeqTrainer\n",
|
| 1557 |
+
"final_dir = \"/content/drive/MyDrive/llm-low-resource-translator/t5_multilingual/final\"\n",
|
| 1558 |
+
"training_args = Seq2SeqTrainingArguments(\n",
|
| 1559 |
+
" output_dir=final_dir,\n",
|
| 1560 |
+
" eval_strategy=\"epoch\",\n",
|
| 1561 |
+
" learning_rate=3e-4,\n",
|
| 1562 |
+
" per_device_train_batch_size=16,\n",
|
| 1563 |
+
" per_device_eval_batch_size=16,\n",
|
| 1564 |
+
" weight_decay=0.01,\n",
|
| 1565 |
+
" save_total_limit=3,\n",
|
| 1566 |
+
" num_train_epochs=3,\n",
|
| 1567 |
+
" predict_with_generate=True,\n",
|
| 1568 |
+
" fp16=True,\n",
|
| 1569 |
+
" push_to_hub=False,\n",
|
| 1570 |
+
" logging_steps=100,\n",
|
| 1571 |
+
" report_to=\"none\"\n",
|
| 1572 |
+
")\n",
|
| 1573 |
+
"\n",
|
| 1574 |
+
"trainer = Seq2SeqTrainer(\n",
|
| 1575 |
+
" model=model,\n",
|
| 1576 |
+
" args=training_args,\n",
|
| 1577 |
+
" train_dataset=tokenized_datasets[\"train\"],\n",
|
| 1578 |
+
" eval_dataset=tokenized_datasets[\"test\"],\n",
|
| 1579 |
+
" tokenizer=tokenizer,\n",
|
| 1580 |
+
" data_collator=data_collator,\n",
|
| 1581 |
+
" compute_metrics=compute_metrics\n",
|
| 1582 |
+
")"
|
| 1583 |
+
],
|
| 1584 |
+
"metadata": {
|
| 1585 |
+
"colab": {
|
| 1586 |
+
"base_uri": "https://localhost:8080/"
|
| 1587 |
+
},
|
| 1588 |
+
"id": "wSKrfrez8gjV",
|
| 1589 |
+
"outputId": "0a0f5b30-3386-4fed-e350-9c59e0c57f17"
|
| 1590 |
+
},
|
| 1591 |
+
"execution_count": 17,
|
| 1592 |
+
"outputs": [
|
| 1593 |
+
{
|
| 1594 |
+
"output_type": "stream",
|
| 1595 |
+
"name": "stderr",
|
| 1596 |
+
"text": [
|
| 1597 |
+
"/tmp/ipython-input-2730798205.py:19: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.\n",
|
| 1598 |
+
" trainer = Seq2SeqTrainer(\n"
|
| 1599 |
+
]
|
| 1600 |
+
}
|
| 1601 |
+
]
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"cell_type": "markdown",
|
| 1605 |
+
"source": [
|
| 1606 |
+
"## 8. Train the Model"
|
| 1607 |
+
],
|
| 1608 |
+
"metadata": {
|
| 1609 |
+
"id": "uyPpu8Aq8gjV"
|
| 1610 |
+
}
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"cell_type": "code",
|
| 1614 |
+
"source": [
|
| 1615 |
+
"trainer.train()"
|
| 1616 |
+
],
|
| 1617 |
+
"metadata": {
|
| 1618 |
+
"colab": {
|
| 1619 |
+
"base_uri": "https://localhost:8080/",
|
| 1620 |
+
"height": 427
|
| 1621 |
+
},
|
| 1622 |
+
"id": "xKYHdZWq8gjV",
|
| 1623 |
+
"outputId": "b2bd7c13-d758-49e8-c54a-c7d70cd28e35"
|
| 1624 |
+
},
|
| 1625 |
+
"execution_count": 18,
|
| 1626 |
+
"outputs": [
|
| 1627 |
+
{
|
| 1628 |
+
"output_type": "stream",
|
| 1629 |
+
"name": "stderr",
|
| 1630 |
+
"text": [
|
| 1631 |
+
"/usr/local/lib/python3.12/dist-packages/torch/utils/data/dataloader.py:666: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used.\n",
|
| 1632 |
+
" warnings.warn(warn_msg)\n"
|
| 1633 |
+
]
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"output_type": "display_data",
|
| 1637 |
+
"data": {
|
| 1638 |
+
"text/plain": [
|
| 1639 |
+
"<IPython.core.display.HTML object>"
|
| 1640 |
+
],
|
| 1641 |
+
"text/html": [
|
| 1642 |
+
"\n",
|
| 1643 |
+
" <div>\n",
|
| 1644 |
+
" \n",
|
| 1645 |
+
" <progress value='136' max='13986' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
| 1646 |
+
" [ 136/13986 42:16 < 72:48:56, 0.05 it/s, Epoch 0.03/3]\n",
|
| 1647 |
+
" </div>\n",
|
| 1648 |
+
" <table border=\"1\" class=\"dataframe\">\n",
|
| 1649 |
+
" <thead>\n",
|
| 1650 |
+
" <tr style=\"text-align: left;\">\n",
|
| 1651 |
+
" <th>Epoch</th>\n",
|
| 1652 |
+
" <th>Training Loss</th>\n",
|
| 1653 |
+
" <th>Validation Loss</th>\n",
|
| 1654 |
+
" </tr>\n",
|
| 1655 |
+
" </thead>\n",
|
| 1656 |
+
" <tbody>\n",
|
| 1657 |
+
" </tbody>\n",
|
| 1658 |
+
"</table><p>"
|
| 1659 |
+
]
|
| 1660 |
+
},
|
| 1661 |
+
"metadata": {}
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"output_type": "error",
|
| 1665 |
+
"ename": "KeyboardInterrupt",
|
| 1666 |
+
"evalue": "",
|
| 1667 |
+
"traceback": [
|
| 1668 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 1669 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
| 1670 |
+
"\u001b[0;32m/tmp/ipython-input-4032920361.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
|
| 1671 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 2323\u001b[0m \u001b[0mhf_hub_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menable_progress_bars\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2324\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2325\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 2326\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2327\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
| 1672 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 2672\u001b[0m )\n\u001b[1;32m 2673\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2674\u001b[0;31m \u001b[0mtr_loss_step\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtraining_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_items_in_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2675\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2676\u001b[0m if (\n",
|
| 1673 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtraining_step\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m 4069\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"scale_wrt_gas\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4070\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4071\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maccelerator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4072\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4073\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdetach\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
| 1674 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/accelerate/accelerator.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, loss, **kwargs)\u001b[0m\n\u001b[1;32m 2738\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlomo_backward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlearning_rate\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2739\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2740\u001b[0;31m \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2741\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2742\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mset_trigger\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
| 1675 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/torch/_tensor.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m 645\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 646\u001b[0m )\n\u001b[0;32m--> 647\u001b[0;31m torch.autograd.backward(\n\u001b[0m\u001b[1;32m 648\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 649\u001b[0m )\n",
|
| 1676 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/torch/autograd/__init__.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m 352\u001b[0m \u001b[0;31m# some Python versions print out the first line of a multi-line function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 353\u001b[0m \u001b[0;31m# calls in the traceback and some print out the last line\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 354\u001b[0;31m _engine_run_backward(\n\u001b[0m\u001b[1;32m 355\u001b[0m \u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 356\u001b[0m \u001b[0mgrad_tensors_\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
| 1677 |
+
"\u001b[0;32m/usr/local/lib/python3.12/dist-packages/torch/autograd/graph.py\u001b[0m in \u001b[0;36m_engine_run_backward\u001b[0;34m(t_outputs, *args, **kwargs)\u001b[0m\n\u001b[1;32m 827\u001b[0m \u001b[0munregister_hooks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_register_logging_hooks_on_whole_graph\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mt_outputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 828\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 829\u001b[0;31m return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass\n\u001b[0m\u001b[1;32m 830\u001b[0m \u001b[0mt_outputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 831\u001b[0m ) # Calls into the C++ engine to run the backward pass\n",
|
| 1678 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
| 1679 |
+
]
|
| 1680 |
+
}
|
| 1681 |
+
]
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"cell_type": "markdown",
|
| 1685 |
+
"source": [
|
| 1686 |
+
"## 9. Inference Example"
|
| 1687 |
+
],
|
| 1688 |
+
"metadata": {
|
| 1689 |
+
"id": "7NiOt4SY8gjW"
|
| 1690 |
+
}
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"cell_type": "code",
|
| 1694 |
+
"source": [
|
| 1695 |
+
"text = \"Hello, how are you today? I hope you're doing well.\"\n",
|
| 1696 |
+
"\n",
|
| 1697 |
+
"inputs = tokenizer(text, return_tensors=\"pt\").to(model.device)\n",
|
| 1698 |
+
"generated_ids = model.generate(\n",
|
| 1699 |
+
" inputs[\"input_ids\"],\n",
|
| 1700 |
+
" max_length=128,\n",
|
| 1701 |
+
" num_beams=5,\n",
|
| 1702 |
+
" early_stopping=True\n",
|
| 1703 |
+
")\n",
|
| 1704 |
+
"print(generated_ids)\n",
|
| 1705 |
+
"translation = tokenizer.decode(generated_ids[0], skip_special_tokens=True)\n",
|
| 1706 |
+
"print(\"English:\", text)\n",
|
| 1707 |
+
"print(\"German:\", translation)"
|
| 1708 |
+
],
|
| 1709 |
+
"metadata": {
|
| 1710 |
+
"id": "YKCXr6Ap8gjW"
|
| 1711 |
+
},
|
| 1712 |
+
"execution_count": null,
|
| 1713 |
+
"outputs": []
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"cell_type": "markdown",
|
| 1717 |
+
"source": [
|
| 1718 |
+
"## 10. Save Model (Optional)"
|
| 1719 |
+
],
|
| 1720 |
+
"metadata": {
|
| 1721 |
+
"id": "Y_nlerIE8gjW"
|
| 1722 |
+
}
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"cell_type": "code",
|
| 1726 |
+
"source": [
|
| 1727 |
+
"import os\n",
|
| 1728 |
+
"\n",
|
| 1729 |
+
"os.makedirs(final_dir, exist_ok=True)\n",
|
| 1730 |
+
"\n",
|
| 1731 |
+
"trainer.save_model(final_dir)\n",
|
| 1732 |
+
"tokenizer.save_pretrained(final_dir)\n",
|
| 1733 |
+
"print(f\"SAVED TO DRIVE: {final_dir}\")\n"
|
| 1734 |
+
],
|
| 1735 |
+
"metadata": {
|
| 1736 |
+
"colab": {
|
| 1737 |
+
"base_uri": "https://localhost:8080/"
|
| 1738 |
+
},
|
| 1739 |
+
"id": "guMiVDeT8gjW",
|
| 1740 |
+
"outputId": "1ab58e4d-2dd6-441b-ef48-bec14a4a445e"
|
| 1741 |
+
},
|
| 1742 |
+
"execution_count": 34,
|
| 1743 |
+
"outputs": [
|
| 1744 |
+
{
|
| 1745 |
+
"output_type": "execute_result",
|
| 1746 |
+
"data": {
|
| 1747 |
+
"text/plain": [
|
| 1748 |
+
"('./mt5-en-de-finetuned/tokenizer_config.json',\n",
|
| 1749 |
+
" './mt5-en-de-finetuned/special_tokens_map.json',\n",
|
| 1750 |
+
" './mt5-en-de-finetuned/spiece.model',\n",
|
| 1751 |
+
" './mt5-en-de-finetuned/added_tokens.json')"
|
| 1752 |
+
]
|
| 1753 |
+
},
|
| 1754 |
+
"metadata": {},
|
| 1755 |
+
"execution_count": 34
|
| 1756 |
+
}
|
| 1757 |
+
]
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"cell_type": "markdown",
|
| 1761 |
+
"source": [
|
| 1762 |
+
"---\n",
|
| 1763 |
+
"\n",
|
| 1764 |
+
"**Done!** You now have a fine-tuned mT5 model for **English → German** translation.\n",
|
| 1765 |
+
"\n",
|
| 1766 |
+
"To adapt to **any other language**, just change:\n",
|
| 1767 |
+
"- `wmt16` → another dataset (e.g., `opus100`, `flores200`)\n",
|
| 1768 |
+
"- `source_lang`, `target_lang` keys\n",
|
| 1769 |
+
"- Dataset name in `load_dataset()`\n",
|
| 1770 |
+
"\n",
|
| 1771 |
+
"Let me know if you want a version for **low-resource languages** (e.g., Swahili, Quechua)!"
|
| 1772 |
+
],
|
| 1773 |
+
"metadata": {
|
| 1774 |
+
"id": "4RwTey1F8gjW"
|
| 1775 |
+
}
|
| 1776 |
+
}
|
| 1777 |
+
]
|
| 1778 |
+
}
|